With ecological theory followed during disposition and application of landscape plants in residential area as the guidance,ecological landscape concept was established.It emphasized that landscape plants disposition s...With ecological theory followed during disposition and application of landscape plants in residential area as the guidance,ecological landscape concept was established.It emphasized that landscape plants disposition should aim at making the nature reappear,ameliorating and maintaining ecological balance in residential area,with harmonious coexistence between human and nature as the goal,and with systematicness of landscape greening,diversity of biological development and sustainability of plant landscaping as the mission,so as to achieve plane systematicness,spatial hierarchy and temporal relevance.展开更多
The semantic segmentation of a bird’s-eye view(BEV)is crucial for environment perception in autonomous driving,which includes the static elements of the scene,such as drivable areas,and dynamic elements such as cars....The semantic segmentation of a bird’s-eye view(BEV)is crucial for environment perception in autonomous driving,which includes the static elements of the scene,such as drivable areas,and dynamic elements such as cars.This paper proposes an end-to-end deep learning architecture based on 3D convolution to predict the semantic segmentation of a BEV,as well as voxel semantic segmentation,from monocular images.The voxelization of scenes and feature transformation from the perspective space to camera space are the key approaches of this model to boost the prediction accuracy.The effectiveness of the proposed method was demonstrated by training and evaluating the model on the NuScenes dataset.A comparison with other state-of-the-art methods showed that the proposed approach outperformed other approaches in the semantic segmentation of a BEV.It also implements voxel semantic segmentation,which cannot be achieved by the state-of-the-art methods.展开更多
A detailed research in soil improving measure was conducted during the process of plants that were cultivated in Tianjin saline and alkaline area. The results showed that the commonly used measures could improve the s...A detailed research in soil improving measure was conducted during the process of plants that were cultivated in Tianjin saline and alkaline area. The results showed that the commonly used measures could improve the soil, and also we got some useful advices and suggestions for plants cultivating in Tianiin saline and alkaline areas.展开更多
The last decades have witnessed a rapid development of noninvasive plant phenotyping,capable of detecting plant stress scale levels from the subcellular to the whole population scale.However,even with such a broad ran...The last decades have witnessed a rapid development of noninvasive plant phenotyping,capable of detecting plant stress scale levels from the subcellular to the whole population scale.However,even with such a broad range,most phenotyping objects are often just concerned with leaves.This review offers a unique perspective of noninvasive plant stress phenotyping from a multi-organ view.First,plant sensing and responding to abiotic stress from the diverse vegetative organs(leaves,stems,and roots)and the interplays between these vital components are analyzed.Then,the corresponding noninvasive optical phenotyping techniques are also provided,which can prompt the practical implementation of appropriate noninvasive phenotyping techniques for each organ.Furthermore,we explore methods for analyzing compound stress situations,as field conditions frequently encompass multiple abiotic stressors.Thus,our work goes beyond the conventional approach of focusing solely on individual plant organs.The novel insights of the multi-organ,noninvasive phenotyping study provide a reference for testing hypotheses concerning the intricate dynamics of plant stress responses,as well as the potential interactive effects among various stressors.展开更多
Through the investigation on influence of temperature, humidity and effects of landscape in Harbin First Department Store （Hayibai） Center Recreational Square, the influence of landscape designing of plant on the en...Through the investigation on influence of temperature, humidity and effects of landscape in Harbin First Department Store （Hayibai） Center Recreational Square, the influence of landscape designing of plant on the environment was researched. Two improved suggestions were given after analyzing the results of the investigation. One is to further plan the market of designing of city recreational square, and to manage and maintain the city recreational square; the other is to make good policies to control and avoid some large scale political projects.展开更多
为满足高通量作物表型分析需求,提升三维点云重建效率和精度,该研究针对不同作物、不同生育时期、不同植株部位(地上部和根系),基于研发的多视角自动成像系统和SFM(structure from motion)-MVS(multi-view stereo)算法,采用不同视角和...为满足高通量作物表型分析需求,提升三维点云重建效率和精度,该研究针对不同作物、不同生育时期、不同植株部位(地上部和根系),基于研发的多视角自动成像系统和SFM(structure from motion)-MVS(multi-view stereo)算法,采用不同视角和不同相机数获取的图像重建作物三维点云,通过重建效率和精度(Hausdorff距离)评估,以及基于点云提取表型参数(株高、幅宽、凸包体积和总表面积)的可靠性评价,优化作物三维点云重建策略。结果显示,对于结构相对稀松、遮挡较少的盆栽植株(苗期、蕾薹期、盛花期、成熟期油菜)、结构相对紧凑、遮挡较多的植株地上部(花铃期棉花、抽穗期水稻、拔节期和灌浆期小麦)以及器官密集、遮挡严重且有较多细长结构的地上部和根系(分蘖期小麦和成熟期水稻地上部、成熟期玉米和油菜根系),分别采用3~4、6和10个相机为其最优重建策略(Hausdorff距离小于或接近0.20 cm,且重建时长和Hausdorff距离归一化值之和最小)。采用不少于4个相机获取的图像重建作物三维点云,可提取较为可靠的表型参数(决定系数R2>0.90,相对均方根误差RRMSE≤9%)。该研究提出的最优重建策略平衡了自动成像系统构建成本、三维重建效率和精度以及适用植株复杂程度,为实现多种作物高效、低成本、高精度三维重建和表型参数提取提供了重要依据。展开更多
建筑室内空间是城市居民主要的生产生活空间,对健康具有重要的影响。其中,室内植物和窗景是促进健康的关键要素,但鲜有从室内视角揭示室内植物和窗外植物景观对人整体健康效益的影响。基于Web of Science(WoS)和中国知网(CNKI)两个数据...建筑室内空间是城市居民主要的生产生活空间,对健康具有重要的影响。其中,室内植物和窗景是促进健康的关键要素,但鲜有从室内视角揭示室内植物和窗外植物景观对人整体健康效益的影响。基于Web of Science(WoS)和中国知网(CNKI)两个数据库,遴选2000-2023年针对室内植物和窗外植物对健康影响研究的中英文文献,应用文献计量方法分析知识网络关系,论述室内外植物景观对健康的影响效应。主要从心理健康、行为认知和生理健康三个方面分析室内外植物促进人体健康可能存在的影响机制以及室内外植物对健康的影响差异。指出今后研究应拓宽研究群体结构和室内空间多样性研究、重视室内与室外绿色空间的连续性、拓展室内外植物类别与特征研究、积极探索多环境因素和多感官交互对健康的影响研究、构建多模态数据融合模型分析室内外植物对身心健康的影响。以期为国内城市健康人居环境设计提供指导。展开更多
基金Supported by Education Department of Anhui Province (Characteristic Subject Construction of Anhui Province)~~
文摘With ecological theory followed during disposition and application of landscape plants in residential area as the guidance,ecological landscape concept was established.It emphasized that landscape plants disposition should aim at making the nature reappear,ameliorating and maintaining ecological balance in residential area,with harmonious coexistence between human and nature as the goal,and with systematicness of landscape greening,diversity of biological development and sustainability of plant landscaping as the mission,so as to achieve plane systematicness,spatial hierarchy and temporal relevance.
基金the National Natural Science Founda-tion of China(No.52072243)the Sichuan Science and Technology Program(No.2020YFSY0058)。
文摘The semantic segmentation of a bird’s-eye view(BEV)is crucial for environment perception in autonomous driving,which includes the static elements of the scene,such as drivable areas,and dynamic elements such as cars.This paper proposes an end-to-end deep learning architecture based on 3D convolution to predict the semantic segmentation of a BEV,as well as voxel semantic segmentation,from monocular images.The voxelization of scenes and feature transformation from the perspective space to camera space are the key approaches of this model to boost the prediction accuracy.The effectiveness of the proposed method was demonstrated by training and evaluating the model on the NuScenes dataset.A comparison with other state-of-the-art methods showed that the proposed approach outperformed other approaches in the semantic segmentation of a BEV.It also implements voxel semantic segmentation,which cannot be achieved by the state-of-the-art methods.
文摘A detailed research in soil improving measure was conducted during the process of plants that were cultivated in Tianjin saline and alkaline area. The results showed that the commonly used measures could improve the soil, and also we got some useful advices and suggestions for plants cultivating in Tianiin saline and alkaline areas.
基金supported by the Natural Science Foundation of Fujian Province,China(2022J01611)Subsidy for the Construction of Fujian Key Laboratory of Agricultural Information Sensing Technology(KJG22052A)+2 种基金Agricultural Artificial Intelligence(133/71202020)Subtropical Fruit Intelligent Production Service Team(11899170167)the Program of Interdisciplinary Integration Promoting the Development of Intelligent Agriculture(Horticulture)(No.000-71202103B).
文摘The last decades have witnessed a rapid development of noninvasive plant phenotyping,capable of detecting plant stress scale levels from the subcellular to the whole population scale.However,even with such a broad range,most phenotyping objects are often just concerned with leaves.This review offers a unique perspective of noninvasive plant stress phenotyping from a multi-organ view.First,plant sensing and responding to abiotic stress from the diverse vegetative organs(leaves,stems,and roots)and the interplays between these vital components are analyzed.Then,the corresponding noninvasive optical phenotyping techniques are also provided,which can prompt the practical implementation of appropriate noninvasive phenotyping techniques for each organ.Furthermore,we explore methods for analyzing compound stress situations,as field conditions frequently encompass multiple abiotic stressors.Thus,our work goes beyond the conventional approach of focusing solely on individual plant organs.The novel insights of the multi-organ,noninvasive phenotyping study provide a reference for testing hypotheses concerning the intricate dynamics of plant stress responses,as well as the potential interactive effects among various stressors.
文摘Through the investigation on influence of temperature, humidity and effects of landscape in Harbin First Department Store （Hayibai） Center Recreational Square, the influence of landscape designing of plant on the environment was researched. Two improved suggestions were given after analyzing the results of the investigation. One is to further plan the market of designing of city recreational square, and to manage and maintain the city recreational square; the other is to make good policies to control and avoid some large scale political projects.
文摘为满足高通量作物表型分析需求,提升三维点云重建效率和精度,该研究针对不同作物、不同生育时期、不同植株部位(地上部和根系),基于研发的多视角自动成像系统和SFM(structure from motion)-MVS(multi-view stereo)算法,采用不同视角和不同相机数获取的图像重建作物三维点云,通过重建效率和精度(Hausdorff距离)评估,以及基于点云提取表型参数(株高、幅宽、凸包体积和总表面积)的可靠性评价,优化作物三维点云重建策略。结果显示,对于结构相对稀松、遮挡较少的盆栽植株(苗期、蕾薹期、盛花期、成熟期油菜)、结构相对紧凑、遮挡较多的植株地上部(花铃期棉花、抽穗期水稻、拔节期和灌浆期小麦)以及器官密集、遮挡严重且有较多细长结构的地上部和根系(分蘖期小麦和成熟期水稻地上部、成熟期玉米和油菜根系),分别采用3~4、6和10个相机为其最优重建策略(Hausdorff距离小于或接近0.20 cm,且重建时长和Hausdorff距离归一化值之和最小)。采用不少于4个相机获取的图像重建作物三维点云,可提取较为可靠的表型参数(决定系数R2>0.90,相对均方根误差RRMSE≤9%)。该研究提出的最优重建策略平衡了自动成像系统构建成本、三维重建效率和精度以及适用植株复杂程度,为实现多种作物高效、低成本、高精度三维重建和表型参数提取提供了重要依据。
文摘建筑室内空间是城市居民主要的生产生活空间,对健康具有重要的影响。其中,室内植物和窗景是促进健康的关键要素,但鲜有从室内视角揭示室内植物和窗外植物景观对人整体健康效益的影响。基于Web of Science(WoS)和中国知网(CNKI)两个数据库,遴选2000-2023年针对室内植物和窗外植物对健康影响研究的中英文文献,应用文献计量方法分析知识网络关系,论述室内外植物景观对健康的影响效应。主要从心理健康、行为认知和生理健康三个方面分析室内外植物促进人体健康可能存在的影响机制以及室内外植物对健康的影响差异。指出今后研究应拓宽研究群体结构和室内空间多样性研究、重视室内与室外绿色空间的连续性、拓展室内外植物类别与特征研究、积极探索多环境因素和多感官交互对健康的影响研究、构建多模态数据融合模型分析室内外植物对身心健康的影响。以期为国内城市健康人居环境设计提供指导。
